Business Research Methods

Hypothesis Testing

http://www.facebook.com/mr.fortyseven

Topics to be covered
Hypothesis : Meaning, Types, characteristics, sources. Formulation of Hypothesis, Errors in hypothesis testing Parametric and Nonparametric test T-test, Z-test, F-test, U-test, RankSum Test, K-W Test.

http://www.facebook.com/mr.fortyseven

Hypothesis - Meaning
A hypothesis is a tentative assumption relating to certain phenomenon, which the researcher wants to verify when required. It is an unproven statement or proposition about a factor or phenomenon that is of interest to the researcher. An important role of a hypothesis is to suggest variables to be included in the research design.

http://www.facebook.com/mr.fortyseven

Development of Research Questions and Hypotheses

Objective/ Theoretica l Framewor k

Research Questions

Analytical Model

Hypothesis

http://www.facebook.com/mr.fortyseven

Types of Hypothesis

Descriptive Hypothesis These by name implies describing some characteristics of an object, a situation, an individual or even an organization. Eg. Why do youngsters prefer to watch MTV Channel? Relational Hypothesis In this case we describe relationship between 2 variables. Eg. Rate of attrition is high in those jobs where there is night shift working. Working Hypothesis This is a hypothesis framed in the early stages of research. These are altered or modified as investigation proceeds. Eg. As of now, demand and quality are related. Later on this may not be the fact as investigation proceeds. Common Sense Hypothesis Based on what is being observed. Eg. Economically poor students work hard, compared to those , who come from well to do families.

http://www.facebook.com/mr.fortyseven

Null Hypothesis This hypothesis states that there is no difference between the parameter and the statistic that is being computed. Eg There is no significant difference between the performance of the employees of a bank working in two different branches. Analytical Hypothesis Here relationship of analytical variable is found. These are used when one would like to specify the relationship between changes in one property leading to change in another. Eg. Income level related to number of children in the family.

http://www.facebook.com/mr.fortyseven

Sources of Hypothesis

Theory- Theory on the subject can act as a source of hypothesis. We start of from a general premise and then formulate hypothesis. Eg. Providing employment opportunity is an indicator of social responsibility of a government enterprise. From the above hypothesis, it can be deduced that: 1. Public enterprise has greater social concern than other enterprises. 2. Peoples perception of government enterprise is social concern. 3. Govt. enterprise help in improving the life of less privileged people. Observation Peoples behavior is observed. In this method we use observed behavior to infer the attitudes. Eg. A shopper in a supermarket may be disguised, to watch the customer in the stores. The following may be observed: a) How the customer approaches the Product category, b) How long he/she spends in front of display, c) Whether the customer had difficulty in locating the product. Collect all these data and formulate a hypothesis regarding the behavior of the customer towards the product.
http://www.facebook.com/mr.fortyseven

Past experience Here researcher goes by past experience to formulate the hypothesis. Eg. A dealer may state that fastest moving kids apparel is frock. This may be verified. Case studies Normally this is done before the launch of a product to find customer taste and preferences. Similarity This could be with respect to similarity in activities of human beings. Eg. Dress, food habits or any other activities found in human life in different parts of the globe.

http://www.facebook.com/mr.fortyseven

Characteristics of a Hypothesis

Clarity of concepts Concepts should not be abstract. If concepts are not clear, precise problem formulation will be difficult leading to difficulty in data collection. Concepts are important because, it means different to different people. Eg. Wearing a sunglass represents a life style for a student, whereas it is an eye protecting device to a doctor. Ability to test It should be possible to verify the hypothesis. Therefore, a good hypothesis is one in which there is empirical evidence. For eg. Sales of Pantaloons is 20% higher than the sales of Shoppers Stop.
http://www.facebook.com/mr.fortyseven

Specific/Clear What is to be tested should be clear. The relationship between the variables should be clear or the statistic under verification should be mentioned clearly. Eg. Two wheeler manufactured by company A gives better mileage than that manufactured by company B. Here what is to be verified is clear and specific. Statistical Tools Hypothesis should be such that, it is possible to use statistical techniques. Such as Anova, Chi square, t- test or other non parametric tests.

http://www.facebook.com/mr.fortyseven

Logical If there is two or more Hypothesis derived from the same basic theory, they should not contradict each other. Eg. Study of MBA gives us practical knowledge. Anshul has completed his MBA program. Anshul has got practical knowledge. Subjectivity Researchers subjectivity or his biased Judgment should be eliminated from the hypothesis. Eg. Older sales man sells less than younger salesman. This may be a biased opinion. As a matter of fact, older salesman may be selling more due to their experience and rapport developed with the customer. Theory Hypothesis must be supported or backed up by theoretical relevance. Eg. Attitude of customer towards a new product introduction. This study is very well backed up by theory on consumer behavior.

http://www.facebook.com/mr.fortyseven

Steps involved in Hypothesis Testing Formulate H0 and H1

Reject or do not reject H0. Draw a marketing researchhttp://www.facebook.com/mr.fortyseven conclusion.

Does the test statistic fall in the critical region

No Accept the null hypothesis

Yes

Reject Null Hypothesis

http://www.facebook.com/mr.fortyseven

Steps of Hypothesis Testing

Formulate the Hypothesis The first step is to formulate the null and alternative hypothesis. A null hypothesis is a statement of no difference or no effect. If the null hypothesis is not rejected, no changes will be made. An alternative hypothesis is one in which some difference or effect is expected. Thus the alternative hypothesis is the opposite of the null hypothesis. The null hypothesis is always the hypothesis that is tested. The null hypothesis refers to a specified value of the population parameter (eg. , etc.).
http://www.facebook.com/mr.fortyseven

For eg. A major department store is considering the introduction of an internet shopping service. The new service will be introduced if more than 40% of the Internet users shop via the internet. The appropriate way to formulate the hypothesis is: H0: 0.40 H1: 0.40 If the null hypothesis H0 is rejected, then the alternative hypothesis H1 will be accepted and the new Internet shopping service introduced. On the other hand, if H0 is not rejected, then the new service should not be introduced unless additional evidence is obtained. This test of the null hypothesis is a one-tailed test, because the alternative hypothesis is expressed directionally: the proportion of Internet users who use the Internet for shopping is greater than 0.40. On the other hand, suppose the researcher wanted to determine whether the proportion of Internet users who shop via the Internet is different than 40%. Then a two tailed test is required, and the hypothesis would be expressed as: H0: = 0.40 H1: 0.40

http://www.facebook.com/mr.fortyseven

Select an Appropriate Test - To test the null hypothesis, it is necessary to select an appropriate statistical technique. The test statistic measures how close the sample has come to the null hypothesis. If the hypothesis pertains to a larger sample (30 or more), the Ztest is used. When the sample is small (less than 30), the T-test is used. Choose Level of Significance, The next step is its validity at a certain level of significance. The confidence with which a null hypothesis is accepted or rejected depends upon the significance level. A significance level of say 5% means that the risk of making a wrong decision is 5%. The researcher is likely to be wrong in accepting false hypothesis or rejecting a true hypothesis by 5 out of 100 occasions.
http://www.facebook.com/mr.fortyseven

Errors: Type I & Type II Errors- Whenever we draw inferences about a population, there is a risk that an incorrect conclusion will be reached. Two types of errors can occur: Type I Error occurs when the sample results lead to the rejection of the null hypothesis when it is in fact true. In our eg. A type I error would occur if we concluded, based on the sample data, that the proportion of customers preferring the new service plan was greater than 0.40, when in fact it was less than or equal to 0.40. The probability of Type I error () is also called the level of significance.
http://www.facebook.com/mr.fortyseven

Type II Error occurs when, based on the sample results, the null hypothesis is not rejected when it is in fact false. In our eg. The Type II error would occur if we concluded, based on sample data, that the proportion of customers, preferring the new service plan was less than or equal to 0.40 when in fact, it was greater than 0.40.The probability of Type II error is denoted by . Power of a test is the probability (1-) of rejecting the null hypothesis when it is false and should be rejected. For a given level of , increasing the sample size will decrease , thereby increasing the power of the test.
http://www.facebook.com/mr.fortyseven

Collect Data and Calculate Test Statistic Sample size is determined after taking into account the desired and errors and other qualitative considerations, such as budget constraints. Then the required data are collected and the value of the test statistic computed using an appropriate statistical test based on the sample size. Determine the Probability / Critical Test Value Find the Probability or Critical Test Value from the statistical table at a given level of significance for the appropriate number of degrees of freedom.

http://www.facebook.com/mr.fortyseven

Compare the Probability (Critical Value) and Make the Decision- Compare the table value with the computed value. Accepting or rejecting the null hypothesis depends on whether the computed value falls in the region of rejection at a given level of significance. If the computed value is higher than the table value, we reject the null hypothesis and conclude that the alternative hypothesis is accepted and vice versa. If probability of TS cal <significance level(), then reject H0. but, if TS cal > TS CR, then reject H0. Marketing Research Conclusion The conclusion reached by hypothesis testing must be expressed in terms of the marketing research problem.
http://www.facebook.com/mr.fortyseven

Parametric Tests
These tests are based on some assumptions about the parent population from which the sample has been drawn. These assumptions can be with respect to sample size, type of distribution or on population parameters like mean, standard deviation etc. Parametric tests are more powerful. The data in this test is derived from interval and ratio measurement. In parametric tests, it is assumed that the data follows normal distributions. Egs. Of parametric tests are Z Test, T-Test and F-Test. Observations must be independent, i.e., selection of nay one item should not affect the

http://www.facebook.com/mr.fortyseven

T-Test (Note: For Formulae refer the handwritten notes) T-Test is a univariate test. Uses t-distribution, which is a symmetrical bell-shaped curve, for testing sample mean and proportion. Assumes that the variable is normally distributed and the mean is known and the population variance is estimated from the sample. It is used when the standard deviation is unknown and the size of sample is small (i.e. less than 30).
http://www.facebook.com/mr.fortyseven

Z-Test
It is a popular test for judging the significance of mean and proportions. It is used for t-distribution and binomial or poisson distribution also when the size of sample is very large (more than 30) on the presumption that such a distribution tends to approximate normal distribution as sample size becomes larger. Testing the hypothesis about difference between two means: This can be used when two population means are given and null hypothesis is H0: P1 = P2.

http://www.facebook.com/mr.fortyseven

F-Test
An F test of sample variance may be performed if it is not known whether the two populations have equal variance. It is used to test the equality of variance of two normal populations i.e. to find whether two samples can be regarded as drawn from normal populations having the same variance. This test is particularly useful when multiple sample cases are involved and the data has been measured on interval or ratio scale. If the probability of F is greater than the significance level , H0 is not rejected. On the other hand, if the probability of F is less than or equal to , H0 is rejected.

http://www.facebook.com/mr.fortyseven

Non Parametric Tests

Non Parametric tests are used to test the hypothesis with nominal and ordinal data. We do not make assumptions about the shape of population distribution. These are distribution-free tests. The hypothesis of non-parametric test is concerned with something other than the value of a population parameter. Easy to compute. There are certain situations particularly in marketing research, where the assumptions of parametric tests are not valid. Examples are Chi-Square Test, Mann Whitney U Test, Kruskal-Wallis Test, Rank Correlation Test.
http://www.facebook.com/mr.fortyseven

Chi-Square Test

The chi square statistic is used to test the statistical significance of the observed association in a cross-tabulation. It assists us in determining whether a systematic association exists between the two variables. The null hypothesis is that there is no association between the variables. The test is conducted by computing the cell frequencies that would be expected if no association were present between the variables, given the existing row and column totals. These expected cell frequencies are then compared to the actual observed frequencies, found in the cross tabulation to calculate the chisquare statistic.
http://www.facebook.com/mr.fortyseven

Wilcoxon-Mann-Whitney Test (U Test)/Rank Sum Test

A statistical test for a variable measured on an ordinal scale comparing the difference in the location of two populations based on observations from two independent samples. This test corresponds to the two-independent sample t test for interval scale variables, when the variances of the two populations are assumed equal. It measures the degree of separation or the amount of overlap between the two groups. The null hypothesis states that the two sets of score do not have differences whereas the alternative hypothesis states that the two sets of scores do differ systematically.

http://www.facebook.com/mr.fortyseven

This involves the following procedure: 1. The data of both the samples are arranged in one column in order of their magnitude either in ascending or descending order. 2. Thereafter ranks are assigned. 3. Then the sum of ranks of 1st sample is obtained denoted as R1 and then the sum of ranks of 2nd sample is obtained denoted as R2. 4. The test statistic U is then calculated.
http://www.facebook.com/mr.fortyseven

Kruskal-Wallis Test/ Rank Sum Test

Kruskal Wallis Test is used when more than two populations are involved. This test will enable us to know whether independent samples have been drawn from the same population or from different populations having the same distribution. This test is an extension of Mann Whitney Test. Mann Whitney Test is used when only two populations are involved and Kruskal-Wallis test is used when more than two populations are involved. This test is also called the H Test.
http://www.facebook.com/mr.fortyseven

Rank Correlation Test

This is used to find out the correlation between two sets of ranks. Eg. Two judges in a beauty competition rank the 10 entrants as follows:
Judge 1 Judge 2 5 4 2 5 3 2 4 1 1 6 6 7 8 10 7 9 10 11 9 12

Rank Correlation test is used to find if there is any correlation between the ranks given by the two judges.
http://www.facebook.com/mr.fortyseven

Imp Questions
Explain Type I and Type II error. (3 Marks) What is a hypothesis? (3 Marks) Explain the procedure for testing hypothesis. (7 Marks) Describe the following tests used in univariate analysis i) chi-square test ii) students t test (10 Marks)

http://www.facebook.com/mr.fortyseven